Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Reinforcement Learning on Stochastic D4RL Hopper Medium MuJoCo
Loading...
1,014
Mean Return
CODAC-C
872.456
909.203
945.95
982.697
Jul 12, 2021
Mean Return
CVaR (0.1)
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Return
CVaR (0.1)
CODAC-C
objective=CVaR
2021.07
1,014
976.4
CODAC-C
Objective=Risk-sensitive
2021.07
1,014
976.4
ORAAC
2021.07
1,007.1
767.6
ORAAC
2021.07
1,007.1
767.6
CODAC-N
objective=risk-neutral
2021.07
993.7
952.5
CODAC-N
Objective=Risk-neutral
2021.07
993.7
952.5
CQL
2021.07
877.9
693
CQL
2021.07
877.9
693
Feedback
Search any
task
Search any
task